sw-jobs-api/scrapers/Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.9-slim

# Set the working directory in the container
WORKDIR /app

# Ensure cron is installed
RUN apt-get update && apt-get install -y cron && rm -rf /var/lib/apt/lists/*

# Install any needed packages specified in requirements.txt
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the current directory contents into the container at /app
COPY . /app

# Set the PATH environment variable
ENV PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"

# Copy the crontab file to the cron.d directory
COPY crontab /etc/cron.d/scraper-cron

# Give execution rights on the cron job
RUN chmod 0644 /etc/cron.d/scraper-cron

# Apply cron job
RUN crontab /etc/cron.d/scraper-cron

# Create the log file to be able to run tail
RUN touch /var/log/cron.log

# Copy the script to run the scraper
COPY run_scraper.sh /usr/local/bin/run_scraper.sh

# Grant execution rights to the script
RUN chmod +x /usr/local/bin/run_scraper.sh

# Run the command on container startup
CMD ["cron", "-f"]